Integration of Visual and Shape Attributes for Object Action Complexes

Our work is oriented towards the idea of developing cognitive capabilities in artificial systems through Object Action Complexes (OACs) [7]. The theory comes up with the claim that objects and actions are inseparably intertwined. Categories of objects are not built by visual appearance only, as very common in computer vision, but by the actions an agent can perform and by attributes perceivable. The core of the OAC concept is constituting objects from a set of attributes, which can be manifold in type (e.g. color, shape, mass, material), to actions. This twofold of attributes and actions provides the base for categories. The work presented here is embedded in the development of an extensible system for providing and evolving attributes, beginning with attributes extractable from visual data.

[1]  T. Duckett.  VOCUS : A Visual Attention System for Object Detection and Goal-directed Search , 2010 .

[2]  Kevin W. Bowyer,et al.  Function from visual analysis and physical interaction: a methodology for recognition of generic classes of objects , 1998, Image Vis. Comput..

[3]  Alessandro Saffiotti,et al.  An introduction to the anchoring problem , 2003, Robotics Auton. Syst..

[4]  K. Yokoi,et al.  Operating Humanoid Robots in Human Environments , 2006 .

[5]  T. Southey,et al.  Object Discovery through Motion, Appearance and Shape , 2006 .

[6]  Vidhya Navalpakkam,et al.  Sharing Resources : Buy Attention , Get Object Recognition , 2022 .

[7]  Dorin Comaniciu,et al.  Mean Shift: A Robust Approach Toward Feature Space Analysis , 2002, IEEE Trans. Pattern Anal. Mach. Intell..

[8]  S Ullman,et al.  Shifts in selective visual attention: towards the underlying neural circuitry. , 1985, Human neurobiology.

[9]  Sangmoon Choi.  Biologically Motivated Visual Attention System Using Bottom-up Saliency Map and Top-down Inhibition , 2004 .

[10]  Giorgio Metta,et al.  Better Vision through Experimental Manipulation , 2002 .

[11]  Jan-Olof Eklundh,et al.  Foveated Figure-Ground Segmentation and Its Role in Recognition , 2005, BMVC.

[12]  Charles C. Kemp,et al.  Manipulation in Human Environments , 2006, 2006 6th IEEE-RAS International Conference on Humanoid Robots.

[13]  Danica Kragic,et al.  Minimum volume bounding box decomposition for shape approximation in robot grasping , 2008, 2008 IEEE International Conference on Robotics and Automation.

[14]  Nick Hawes,et al.  A System for Continuous Learning of Visual Concepts , 2007 .

[15]  Christof Koch,et al.  A Model of Saliency-Based Visual Attention for Rapid Scene Analysis , 2009 .

[16]  Christopher W. Geib,et al.  Object Action Complexes as an Interface for Planning and Robot Control , 2006 .